Implementing a convolution neural network for recognizing poses in images of faces

<p>Convolutional neural networks belong to a set of techniques grouped under deep learning, a branch of machine learning, which has proven successful in recent years in image and voice recording recognition tasks. This paper explores the use of deep convolutional neural networks in the recogni...

Full description

Bibliographic Details
Main Authors: Paul Méndez, Julio Ibarra
Format: Article
Language:English
Published: Universidad San Francisco de Quito USFQ 2014-12-01
Series:ACI Avances en Ciencias e Ingenierías
Subjects:
Online Access:http://revistas.usfq.edu.ec/index.php/avances/article/view/167
_version_ 1797285492542144512
author Paul Méndez
Julio Ibarra
author_facet Paul Méndez
Julio Ibarra
author_sort Paul Méndez
collection DOAJ
description <p>Convolutional neural networks belong to a set of techniques grouped under deep learning, a branch of machine learning, which has proven successful in recent years in image and voice recording recognition tasks. This paper explores the use of deep convolutional neural networks in the recognition of horizontal poses outside the plane. We propose a convolutional neural network architecture based on OpenCV open source libraries for classification of images of human faces within seven default poses. We present in details the optimized design of our architecture and our learning strategy.</p><p>The classifier trained on a set of 2600 images of sizes: 33 &times; 33, 41 &times; 41, 65 &times; 65 y 81 &times; 81, achive an recognition rate of 85%, higher than the 78% achieved with the Eigenfaces algorithm, with nearly the same execution time.</p>
first_indexed 2024-03-07T18:02:56Z
format Article
id doaj.art-c3aa1cf260454918abc48b7a2a4d4d5c
institution Directory Open Access Journal
issn 1390-5384
2528-7788
language English
last_indexed 2024-03-07T18:02:56Z
publishDate 2014-12-01
publisher Universidad San Francisco de Quito USFQ
record_format Article
series ACI Avances en Ciencias e Ingenierías
spelling doaj.art-c3aa1cf260454918abc48b7a2a4d4d5c2024-03-02T10:22:04ZengUniversidad San Francisco de Quito USFQACI Avances en Ciencias e Ingenierías1390-53842528-77882014-12-016210.18272/aci.v6i2.167167Implementing a convolution neural network for recognizing poses in images of facesPaul Méndez0Julio Ibarra1Universidad San Francisco de QuitoUniversidad San Francisco de Quito<p>Convolutional neural networks belong to a set of techniques grouped under deep learning, a branch of machine learning, which has proven successful in recent years in image and voice recording recognition tasks. This paper explores the use of deep convolutional neural networks in the recognition of horizontal poses outside the plane. We propose a convolutional neural network architecture based on OpenCV open source libraries for classification of images of human faces within seven default poses. We present in details the optimized design of our architecture and our learning strategy.</p><p>The classifier trained on a set of 2600 images of sizes: 33 &times; 33, 41 &times; 41, 65 &times; 65 y 81 &times; 81, achive an recognition rate of 85%, higher than the 78% achieved with the Eigenfaces algorithm, with nearly the same execution time.</p>http://revistas.usfq.edu.ec/index.php/avances/article/view/167Red neuronal de convoluciónred neuronal profundareconocimiento de rostrosposesaprendizaje profundo
spellingShingle Paul Méndez
Julio Ibarra
Implementing a convolution neural network for recognizing poses in images of faces
ACI Avances en Ciencias e Ingenierías
Red neuronal de convolución
red neuronal profunda
reconocimiento de rostros
poses
aprendizaje profundo
title Implementing a convolution neural network for recognizing poses in images of faces
title_full Implementing a convolution neural network for recognizing poses in images of faces
title_fullStr Implementing a convolution neural network for recognizing poses in images of faces
title_full_unstemmed Implementing a convolution neural network for recognizing poses in images of faces
title_short Implementing a convolution neural network for recognizing poses in images of faces
title_sort implementing a convolution neural network for recognizing poses in images of faces
topic Red neuronal de convolución
red neuronal profunda
reconocimiento de rostros
poses
aprendizaje profundo
url http://revistas.usfq.edu.ec/index.php/avances/article/view/167
work_keys_str_mv AT paulmendez implementingaconvolutionneuralnetworkforrecognizingposesinimagesoffaces
AT julioibarra implementingaconvolutionneuralnetworkforrecognizingposesinimagesoffaces